Research map / Architectures and efficiency / RNNs and normalization
Efficient Learning of Event-based Dense Representation using Hierarchical Memories with Adaptive Update
Uday Kamal, Saibal Mukhopadhyay
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use adaptive memory update instead of uniform update (ablation) | hierarchical memory network · DSEC-Semantic | latency (ms): 5.8 -> 4.5 | Improved |
| use adaptive memory update instead of uniform update (ablation) | hierarchical memory network · DSEC-Semantic | mIoU: 49.7 -> 49.9 | Improved |
| raise update threshold from 0.5 to 0.7 (ablation) | adaptive update · DSEC-Semantic | mIoU: 49.9 -> 46.8 | Hurt |
| lower update threshold from 0.5 to 0.3 (ablation) | adaptive update · DSEC-Semantic | latency (ms): 4.5 -> 4.8 | Hurt |
| use proposed adaptive hierarchical memory instead of HMNet-L3 | event-based segmentation · DSEC-Semantic | mIoU: 57.1 -> 49.9 mIoU; 13.9 -> 4.5 ms | Mixed |
| use proposed method instead of HMNet-L3 for depth | event-based depth estimation · MVSEC outdoor day1 | REL: 0.254 -> 0.292; latency 6.9 -> 2.3 ms | Mixed |
Closest papers by meaning
- Hierarchical Neural Memory Network for Low Latency Event Processing (CVPR 2023 · similarity 0.90)
- Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception (ICLR 2023 · similarity 0.90)
- Event Camera Data Dense Pre-training (ECCV 2024 · similarity 0.88)
- EventPillars: Pillar-based Efficient Representations for Event Data (AAAI 2025 · similarity 0.88)
- EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation (NeurIPS 2025 · similarity 0.87)
- Efficient Event Camera Data Pretraining with Adaptive Prompt Fusion (ICCV 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
